{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/benchmarking/papers/22","list_of":"/task/benchmarking","task":"Benchmarking","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":22,"pages_in_order":56,"rows_per_page":100,"rows":[2101,2200],"of":5548,"counts":{"archive_papers_tagged":5548,"with_a_code_link":2658,"where_syntology_ran_a_sample":749,"not_listed_spam_title":0,"listed":5548,"listed_where_code_ran":749,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":624,"every_run_a_failure_of_syntologys_instrument":125,"listed_with_a_run_with_no_instrument_failure":624,"listed_every_run_a_failure_of_syntologys_instrument":125,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/benchmarking","prev":"/task/benchmarking/papers/21","next":"/task/benchmarking/papers/23","papers":[{"url":"/paper/swinchex-multi-label-classification-on-chest","slug":"swinchex-multi-label-classification-on-chest","title":"SwinCheX: Multi-label classification on chest X-ray images with transformers","date":"2022-06-09","arxiv_id":"2206.04246","repositories_listed":1,"syntology":null},{"url":"/paper/do-we-need-another-explainable-ai-method","slug":"do-we-need-another-explainable-ai-method","title":"Do We Need Another Explainable AI Method? Toward Unifying Post-hoc XAI Evaluation Methods into an Interactive and Multi-dimensional Benchmark","date":"2022-06-08","arxiv_id":"2207.14160","repositories_listed":1,"syntology":null},{"url":"/paper/fedhpo-b-a-benchmark-suite-for-federated","slug":"fedhpo-b-a-benchmark-suite-for-federated","title":"FedHPO-B: A Benchmark Suite for Federated Hyperparameter Optimization","date":"2022-06-08","arxiv_id":"2206.03966","repositories_listed":1,"syntology":null},{"url":"/paper/revisiting-realistic-test-time-training","slug":"revisiting-realistic-test-time-training","title":"Revisiting Realistic Test-Time Training: Sequential Inference and Adaptation by Anchored Clustering","date":"2022-06-06","arxiv_id":"2206.02721","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/revisiting-realistic-test-time-training#ran","syntology_url":"https://syntology.ai/paper/2206.02721","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.02721"}},"official":{"repos":["gorilla-lab-scut/ttac"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/revisiting-the-video-in-video-language","slug":"revisiting-the-video-in-video-language","title":"Revisiting the \"Video\" in Video-Language Understanding","date":"2022-06-03","arxiv_id":"2206.01720","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":2,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/revisiting-the-video-in-video-language#ran","syntology_url":"https://syntology.ai/paper/2206.01720","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.01720"}},"official":null}},{"url":"/paper/fast-benchmarking-of-accuracy-vs-training","slug":"fast-benchmarking-of-accuracy-vs-training","title":"Fast Benchmarking of Accuracy vs. Training Time with Cyclic Learning Rates","date":"2022-06-02","arxiv_id":"2206.00832","repositories_listed":1,"syntology":null},{"url":"/paper/a-japanese-dataset-for-subjective-and","slug":"a-japanese-dataset-for-subjective-and","title":"A Japanese Dataset for Subjective and Objective Sentiment Polarity Classification in Micro Blog Domain","date":"2022-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/jojajovai-a-parallel-guarani-spanish-corpus","slug":"jojajovai-a-parallel-guarani-spanish-corpus","title":"Jojajovai: A Parallel Guarani-Spanish Corpus for MT Benchmarking","date":"2022-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/needle-in-a-haystack-fast-benchmarking-image","slug":"needle-in-a-haystack-fast-benchmarking-image","title":"Needle In A Haystack, Fast: Benchmarking Image Perceptual Similarity Metrics At Scale","date":"2022-06-01","arxiv_id":"2206.00282","repositories_listed":1,"syntology":null},{"url":"/paper/benchmarking-the-robustness-of-lidar-camera","slug":"benchmarking-the-robustness-of-lidar-camera","title":"Benchmarking the Robustness of LiDAR-Camera Fusion for 3D Object Detection","date":"2022-05-30","arxiv_id":"2205.14951","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":3,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/benchmarking-the-robustness-of-lidar-camera#ran","syntology_url":"https://syntology.ai/paper/2205.14951","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.14951"}},"official":{"repos":["kcyu2014/lidar-camera-robust-benchmark"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/bsnsing-a-decision-tree-induction-method","slug":"bsnsing-a-decision-tree-induction-method","title":"bsnsing: A decision tree induction method based on recursive optimal boolean rule composition","date":"2022-05-30","arxiv_id":"2205.15263","repositories_listed":1,"syntology":null},{"url":"/paper/revisiting-audio-pattern-recognition-for","slug":"revisiting-audio-pattern-recognition-for","title":"AI-enabled Sound Pattern Recognition on Asthma Medication Adherence: Evaluation with the RDA Benchmark Suite","date":"2022-05-30","arxiv_id":"2205.15360","repositories_listed":1,"syntology":null},{"url":"/paper/a-framework-for-generating-informative","slug":"a-framework-for-generating-informative","title":"A Framework for Generating Informative Benchmark Instances","date":"2022-05-29","arxiv_id":"2205.14753","repositories_listed":1,"syntology":null},{"url":"/paper/bias-reduction-via-cooperative-bargaining-in","slug":"bias-reduction-via-cooperative-bargaining-in","title":"Bias Reduction via Cooperative Bargaining in Synthetic Graph Dataset Generation","date":"2022-05-27","arxiv_id":"2205.13901","repositories_listed":1,"syntology":null},{"url":"/paper/bongard-hoi-benchmarking-few-shot-visual","slug":"bongard-hoi-benchmarking-few-shot-visual","title":"Bongard-HOI: Benchmarking Few-Shot Visual Reasoning for Human-Object Interactions","date":"2022-05-27","arxiv_id":"2205.13803","repositories_listed":1,"syntology":null},{"url":"/paper/failure-detection-in-medical-image","slug":"failure-detection-in-medical-image","title":"Failure Detection in Medical Image Classification: A Reality Check and Benchmarking Testbed","date":"2022-05-27","arxiv_id":"2205.14094","repositories_listed":1,"syntology":null},{"url":"/paper/geneva-pushing-the-limit-of-generalizability","slug":"geneva-pushing-the-limit-of-generalizability","title":"GENEVA: Benchmarking Generalizability for Event Argument Extraction with Hundreds of Event Types and Argument Roles","date":"2022-05-25","arxiv_id":"2205.12505","repositories_listed":1,"syntology":null},{"url":"/paper/graph-theoretical-approach-to-robust-3d","slug":"graph-theoretical-approach-to-robust-3d","title":"Graph-theoretical approach to robust 3D normal extraction of LiDAR data","date":"2022-05-23","arxiv_id":"2205.11460","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-effect-of-sample-and-topic-sizes-for","slug":"on-the-effect-of-sample-and-topic-sizes-for","title":"Diversity Over Size: On the Effect of Sample and Topic Sizes for Topic-Dependent Argument Mining Datasets","date":"2022-05-23","arxiv_id":"2205.11472","repositories_listed":1,"syntology":null},{"url":"/paper/pyrelational-a-library-for-active-learning","slug":"pyrelational-a-library-for-active-learning","title":"PyRelationAL: a python library for active learning research and development","date":"2022-05-23","arxiv_id":"2205.11117","repositories_listed":1,"syntology":null},{"url":"/paper/deep-learning-based-synchronization-for","slug":"deep-learning-based-synchronization-for","title":"Deep Learning-Based Synchronization for Uplink NB-IoT","date":"2022-05-22","arxiv_id":"2205.10805","repositories_listed":1,"syntology":null},{"url":"/paper/oracle-mnist-a-realistic-image-dataset-for","slug":"oracle-mnist-a-realistic-image-dataset-for","title":"Oracle-MNIST: a Realistic Image Dataset for Benchmarking Machine Learning Algorithms","date":"2022-05-19","arxiv_id":"2205.09442","repositories_listed":1,"syntology":null},{"url":"/paper/snac-coherence-error-detection-for-narrative","slug":"snac-coherence-error-detection-for-narrative","title":"SNaC: Coherence Error Detection for Narrative Summarization","date":"2022-05-19","arxiv_id":"2205.09641","repositories_listed":1,"syntology":null},{"url":"/paper/the-voiceprivacy-2020-challenge-evaluation","slug":"the-voiceprivacy-2020-challenge-evaluation","title":"The VoicePrivacy 2020 Challenge Evaluation Plan","date":"2022-05-14","arxiv_id":"2205.07123","repositories_listed":1,"syntology":null},{"url":"/paper/federated-learning-under-intermittent-client","slug":"federated-learning-under-intermittent-client","title":"Federated Learning Under Intermittent Client Availability and Time-Varying Communication Constraints","date":"2022-05-13","arxiv_id":"2205.06730","repositories_listed":1,"syntology":null},{"url":"/paper/clinical-prompt-learning-with-frozen-language","slug":"clinical-prompt-learning-with-frozen-language","title":"Clinical Prompt Learning with Frozen Language Models","date":"2022-05-11","arxiv_id":"2205.05535","repositories_listed":1,"syntology":null},{"url":"/paper/individual-fairness-guarantees-for-neural","slug":"individual-fairness-guarantees-for-neural","title":"Individual Fairness Guarantees for Neural Networks","date":"2022-05-11","arxiv_id":"2205.05763","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/individual-fairness-guarantees-for-neural#ran","syntology_url":"https://syntology.ai/paper/2205.05763","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.05763"}},"official":{"repos":["eliasbenussi/nn-cert-individual-fairness"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/structured-flexible-and-robust-benchmarking","slug":"structured-flexible-and-robust-benchmarking","title":"Structured, flexible, and robust: benchmarking and improving large language models towards more human-like behavior in out-of-distribution reasoning tasks","date":"2022-05-11","arxiv_id":"2205.05718","repositories_listed":1,"syntology":null},{"url":"/paper/towards-intersectionality-in-machine-learning","slug":"towards-intersectionality-in-machine-learning","title":"Towards Intersectionality in Machine Learning: Including More Identities, Handling Underrepresentation, and Performing Evaluation","date":"2022-05-10","arxiv_id":"2205.04610","repositories_listed":1,"syntology":null},{"url":"/paper/assigning-species-information-to","slug":"assigning-species-information-to","title":"Assigning Species Information to Corresponding Genes by a Sequence Labeling Framework","date":"2022-05-08","arxiv_id":"2205.03853","repositories_listed":1,"syntology":null},{"url":"/paper/bico-net-regress-globally-match-locally-for","slug":"bico-net-regress-globally-match-locally-for","title":"BiCo-Net: Regress Globally, Match Locally for Robust 6D Pose Estimation","date":"2022-05-07","arxiv_id":"2205.03536","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/bico-net-regress-globally-match-locally-for#ran","syntology_url":"https://syntology.ai/paper/2205.03536","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.03536"}},"official":{"repos":["gorilla-lab-scut/bico-net"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/benchmarking-econometric-and-machine-learning","slug":"benchmarking-econometric-and-machine-learning","title":"Benchmarking Econometric and Machine Learning Methodologies in Nowcasting","date":"2022-05-06","arxiv_id":"2205.03318","repositories_listed":1,"syntology":null},{"url":"/paper/shoerinsics-shoeprint-prediction-for","slug":"shoerinsics-shoeprint-prediction-for","title":"Creating a Forensic Database of Shoeprints from Online Shoe Tread Photos","date":"2022-05-04","arxiv_id":"2205.02361","repositories_listed":1,"syntology":null},{"url":"/paper/benchmarking-post-hoc-interpretability","slug":"benchmarking-post-hoc-interpretability","title":"Benchmarking Post-Hoc Interpretability Approaches for Transformer-based Misogyny Detection","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/mmcoqa-conversational-question-answering-over","slug":"mmcoqa-conversational-question-answering-over","title":"MMCoQA: Conversational Question Answering over Text, Tables, and Images","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/msamsum-towards-benchmarking-multi-lingual-1","slug":"msamsum-towards-benchmarking-multi-lingual-1","title":"MSAMSum: Towards Benchmarking Multi-lingual Dialogue Summarization","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/to-find-waldo-you-need-contextual-cues-1","slug":"to-find-waldo-you-need-contextual-cues-1","title":"To Find Waldo You Need Contextual Cues: Debiasing Who’s Waldo","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/foundational-models-for-continual-learning-an","slug":"foundational-models-for-continual-learning-an","title":"Continual Learning with Foundation Models: An Empirical Study of Latent Replay","date":"2022-04-30","arxiv_id":"2205.00329","repositories_listed":1,"syntology":null},{"url":"/paper/answer-consolidation-formulation-and","slug":"answer-consolidation-formulation-and","title":"Answer Consolidation: Formulation and Benchmarking","date":"2022-04-29","arxiv_id":"2205.00042","repositories_listed":1,"syntology":null},{"url":"/paper/a-collection-of-quality-diversity","slug":"a-collection-of-quality-diversity","title":"A Collection of Quality Diversity Optimization Problems Derived from Hyperparameter Optimization of Machine Learning Models","date":"2022-04-28","arxiv_id":"2204.14061","repositories_listed":1,"syntology":null},{"url":"/paper/benchmarking-the-hooke-jeeves-method-mts-ls1","slug":"benchmarking-the-hooke-jeeves-method-mts-ls1","title":"Benchmarking the Hooke-Jeeves Method, MTS-LS1, and BSrr on the Large-scale BBOB Function Set","date":"2022-04-28","arxiv_id":"2204.13284","repositories_listed":1,"syntology":null},{"url":"/paper/watts-infrastructure-for-open-ended-learning","slug":"watts-infrastructure-for-open-ended-learning","title":"Watts: Infrastructure for Open-Ended Learning","date":"2022-04-28","arxiv_id":"2204.13250","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/watts-infrastructure-for-open-ended-learning#ran","syntology_url":"https://syntology.ai/paper/2204.13250","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.13250"}},"official":{"repos":["aadharna/watts"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/a-global-analysis-of-metrics-used-for","slug":"a-global-analysis-of-metrics-used-for","title":"A global analysis of metrics used for measuring performance in natural language processing","date":"2022-04-25","arxiv_id":"2204.11574","repositories_listed":1,"syntology":null},{"url":"/paper/transformation-interaction-rational","slug":"transformation-interaction-rational","title":"Transformation-Interaction-Rational Representation for Symbolic Regression","date":"2022-04-25","arxiv_id":"2205.06807","repositories_listed":1,"syntology":null},{"url":"/paper/mole-digging-tunnels-through-multimodal-multi","slug":"mole-digging-tunnels-through-multimodal-multi","title":"MOLE: Digging Tunnels Through Multimodal Multi-Objective Landscapes","date":"2022-04-22","arxiv_id":"2204.10848","repositories_listed":1,"syntology":null},{"url":"/paper/radio-galaxy-zoo-using-semi-supervised","slug":"radio-galaxy-zoo-using-semi-supervised","title":"Radio Galaxy Zoo: Using semi-supervised learning to leverage large unlabelled data-sets for radio galaxy classification under data-set shift","date":"2022-04-19","arxiv_id":"2204.08816","repositories_listed":1,"syntology":null},{"url":"/paper/stress-testing-lidar-registration","slug":"stress-testing-lidar-registration","title":"Stress-Testing Point Cloud Registration on Automotive LiDAR","date":"2022-04-16","arxiv_id":"2204.07719","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":7,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/stress-testing-lidar-registration#ran","syntology_url":"https://syntology.ai/paper/2204.07719","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.07719"}},"official":{"repos":["amnondrory/lidarregistration"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/deep-learning-model-solves-change-point","slug":"deep-learning-model-solves-change-point","title":"Deep learning model solves change point detection for multiple change types","date":"2022-04-15","arxiv_id":"2204.07403","repositories_listed":1,"syntology":null},{"url":"/paper/do-you-really-mean-that-content-driven-audio","slug":"do-you-really-mean-that-content-driven-audio","title":"Do You Really Mean That? Content Driven Audio-Visual Deepfake Dataset and Multimodal Method for Temporal Forgery Localization","date":"2022-04-13","arxiv_id":"2204.06228","repositories_listed":1,"syntology":null},{"url":"/paper/from-cnns-to-vision-transformers-a","slug":"from-cnns-to-vision-transformers-a","title":"From Modern CNNs to Vision Transformers: Assessing the Performance, Robustness, and Classification Strategies of Deep Learning Models in Histopathology","date":"2022-04-11","arxiv_id":"2204.05044","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/from-cnns-to-vision-transformers-a#ran","syntology_url":"https://syntology.ai/paper/2204.05044","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.05044"}},"official":{"repos":["hhi-aml/histobenchmark"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/biored-a-comprehensive-biomedical-relation","slug":"biored-a-comprehensive-biomedical-relation","title":"BioRED: A Rich Biomedical Relation Extraction Dataset","date":"2022-04-08","arxiv_id":"2204.04263","repositories_listed":1,"syntology":null},{"url":"/paper/deep-visual-geo-localization-benchmark","slug":"deep-visual-geo-localization-benchmark","title":"Deep Visual Geo-localization Benchmark","date":"2022-04-07","arxiv_id":"2204.03444","repositories_listed":1,"syntology":{"n":13,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/deep-visual-geo-localization-benchmark#ran","syntology_url":"https://syntology.ai/paper/2204.03444","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.03444"}},"official":{"repos":["gmberton/deep-visual-geo-localization-benchmark"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/cleave-scalable-and-edge-native-benchmarking","slug":"cleave-scalable-and-edge-native-benchmarking","title":"CLEAVE: Scalable and Edge-native Benchmarking of Networked Control Systems","date":"2022-04-05","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/dynatask-a-framework-for-creating-dynamic-ai","slug":"dynatask-a-framework-for-creating-dynamic-ai","title":"Dynatask: A Framework for Creating Dynamic AI Benchmark Tasks","date":"2022-04-05","arxiv_id":"2204.01906","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":10,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/dynatask-a-framework-for-creating-dynamic-ai#ran","syntology_url":"https://syntology.ai/paper/2204.01906","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.01906"}},"official":{"repos":["facebookresearch/dynabench"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/coarse-to-fine-q-attention-with-learned-path","slug":"coarse-to-fine-q-attention-with-learned-path","title":"Coarse-to-Fine Q-attention with Learned Path Ranking","date":"2022-04-04","arxiv_id":"2204.01571","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-uncertainty-based-moderation-of","slug":"efficient-uncertainty-based-moderation-of","title":"Efficient, Uncertainty-based Moderation of Neural Networks Text Classifiers","date":"2022-04-04","arxiv_id":"2204.01334","repositories_listed":1,"syntology":null},{"url":"/paper/pmubage-the-benchmarking-assortment-of","slug":"pmubage-the-benchmarking-assortment-of","title":"pmuBAGE: The Benchmarking Assortment of Generated PMU Data for Power System Events -- Part I: Overview and Results","date":"2022-04-03","arxiv_id":"2204.01095","repositories_listed":1,"syntology":null},{"url":"/paper/multi-class-road-user-detection-with-3-1d","slug":"multi-class-road-user-detection-with-3-1d","title":"Multi-Class Road User Detection With 3+1D Radar in the View-of-Delft Dataset","date":"2022-04-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/to-find-waldo-you-need-contextual-cues","slug":"to-find-waldo-you-need-contextual-cues","title":"To Find Waldo You Need Contextual Cues: Debiasing Who's Waldo","date":"2022-03-30","arxiv_id":"2203.16682","repositories_listed":1,"syntology":null},{"url":"/paper/earnings-22-a-practical-benchmark-for-accents","slug":"earnings-22-a-practical-benchmark-for-accents","title":"Earnings-22: A Practical Benchmark for Accents in the Wild","date":"2022-03-29","arxiv_id":"2203.15591","repositories_listed":1,"syntology":null},{"url":"/paper/fantastic-questions-and-where-to-find-them-1","slug":"fantastic-questions-and-where-to-find-them-1","title":"Fantastic Questions and Where to Find Them: FairytaleQA -- An Authentic Dataset for Narrative Comprehension","date":"2022-03-26","arxiv_id":"2203.13947","repositories_listed":1,"syntology":null},{"url":"/paper/visual-abductive-reasoning","slug":"visual-abductive-reasoning","title":"Visual Abductive Reasoning","date":"2022-03-26","arxiv_id":"2203.14040","repositories_listed":1,"syntology":{"n":21,"n_ran":11,"n_constructed":8,"n_ran_checked":8,"n_instrument":3,"n_unverified":10,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"11 ran (of which 8 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 10 unverified","sample_list":"/paper/visual-abductive-reasoning#ran","syntology_url":"https://syntology.ai/paper/2203.14040","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.14040"}},"official":{"repos":["leonnnop/var"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":8,"n_ran_no_instrument_failure":8,"n_unverified":10,"ran_from_kinds":["official"]}}},{"url":"/paper/a-simulation-benchmark-for-vision-based","slug":"a-simulation-benchmark-for-vision-based","title":"Benchmarking Visual Localization for Autonomous Navigation","date":"2022-03-24","arxiv_id":"2203.13048","repositories_listed":1,"syntology":null},{"url":"/paper/minicons-enabling-flexible-behavioral-and","slug":"minicons-enabling-flexible-behavioral-and","title":"minicons: Enabling Flexible Behavioral and Representational Analyses of Transformer Language Models","date":"2022-03-24","arxiv_id":"2203.13112","repositories_listed":1,"syntology":null},{"url":"/paper/an-optical-controlling-environment-and","slug":"an-optical-controlling-environment-and","title":"An Optical Control Environment for Benchmarking Reinforcement Learning Algorithms","date":"2022-03-23","arxiv_id":"2203.12114","repositories_listed":1,"syntology":null},{"url":"/paper/sionna-an-open-source-library-for-next","slug":"sionna-an-open-source-library-for-next","title":"Sionna: An Open-Source Library for Next-Generation Physical Layer Research","date":"2022-03-22","arxiv_id":"2203.11854","repositories_listed":1,"syntology":null},{"url":"/paper/grasp-pre-shape-selection-by-synthetic","slug":"grasp-pre-shape-selection-by-synthetic","title":"Grasp Pre-shape Selection by Synthetic Training: Eye-in-hand Shared Control on the Hannes Prosthesis","date":"2022-03-18","arxiv_id":"2203.09812","repositories_listed":1,"syntology":null},{"url":"/paper/shel5k-an-extended-dataset-and-benchmarking","slug":"shel5k-an-extended-dataset-and-benchmarking","title":"SHEL5K: An Extended Dataset and Benchmarking for Safety Helmet Detection","date":"2022-03-17","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/on-the-usefulness-of-the-fit-on-the-test-view","slug":"on-the-usefulness-of-the-fit-on-the-test-view","title":"On the Usefulness of the Fit-on-the-Test View on Evaluating Calibration of Classifiers","date":"2022-03-16","arxiv_id":"2203.08958","repositories_listed":1,"syntology":{"n":22,"n_ran":17,"n_constructed":0,"n_ran_checked":16,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":1,"n_no_contract":15,"n_pointer_only":1,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 1 violated, 15 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/on-the-usefulness-of-the-fit-on-the-test-view#ran","syntology_url":"https://syntology.ai/paper/2203.08958","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.08958"}},"official":{"repos":["markus93/fit-on-the-test"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":16,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/adatime-a-benchmarking-suite-for-domain","slug":"adatime-a-benchmarking-suite-for-domain","title":"ADATIME: A Benchmarking Suite for Domain Adaptation on Time Series Data","date":"2022-03-15","arxiv_id":"2203.08321","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 2 unverified","sample_list":"/paper/adatime-a-benchmarking-suite-for-domain#ran","syntology_url":"https://syntology.ai/paper/2203.08321","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.08321"}},"official":{"repos":["emadeldeen24/adatime"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/aldi-automatic-and-parameter-less-discord-and","slug":"aldi-automatic-and-parameter-less-discord-and","title":"ALDI++: Automatic and parameter-less discord and outlier detection for building energy load profiles","date":"2022-03-13","arxiv_id":"2203.06618","repositories_listed":1,"syntology":null},{"url":"/paper/rood-mri-benchmarking-the-robustness-of-deep","slug":"rood-mri-benchmarking-the-robustness-of-deep","title":"ROOD-MRI: Benchmarking the robustness of deep learning segmentation models to out-of-distribution and corrupted data in MRI","date":"2022-03-11","arxiv_id":"2203.06060","repositories_listed":1,"syntology":null},{"url":"/paper/clearpose-large-scale-transparent-object","slug":"clearpose-large-scale-transparent-object","title":"ClearPose: Large-scale Transparent Object Dataset and Benchmark","date":"2022-03-08","arxiv_id":"2203.03890","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/clearpose-large-scale-transparent-object#ran","syntology_url":"https://syntology.ai/paper/2203.03890","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.03890"}},"official":{"repos":["opipari/clearpose"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/quasi-balanced-self-training-on-noise-aware","slug":"quasi-balanced-self-training-on-noise-aware","title":"Quasi-Balanced Self-Training on Noise-Aware Synthesis of Object Point Clouds for Closing Domain Gap","date":"2022-03-08","arxiv_id":"2203.03833","repositories_listed":1,"syntology":{"n":15,"n_ran":13,"n_constructed":0,"n_ran_checked":12,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":11,"n_pointer_only":1,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 1 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/quasi-balanced-self-training-on-noise-aware#ran","syntology_url":"https://syntology.ai/paper/2203.03833","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.03833"}},"official":{"repos":["gorilla-lab-scut/qs3"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/imagenet-patch-a-dataset-for-benchmarking","slug":"imagenet-patch-a-dataset-for-benchmarking","title":"ImageNet-Patch: A Dataset for Benchmarking Machine Learning Robustness against Adversarial Patches","date":"2022-03-07","arxiv_id":"2203.04412","repositories_listed":1,"syntology":null},{"url":"/paper/survset-an-open-source-time-to-event-dataset","slug":"survset-an-open-source-time-to-event-dataset","title":"SurvSet: An open-source time-to-event dataset repository","date":"2022-03-07","arxiv_id":"2203.03094","repositories_listed":1,"syntology":null},{"url":"/paper/the-importance-of-being-constrained-dealing","slug":"the-importance-of-being-constrained-dealing","title":"The importance of being constrained: dealing with infeasible solutions in Differential Evolution and beyond","date":"2022-03-07","arxiv_id":"2203.03512","repositories_listed":1,"syntology":null},{"url":"/paper/a-large-scale-comprehensive-dataset-and-copy","slug":"a-large-scale-comprehensive-dataset-and-copy","title":"A Large-scale Comprehensive Dataset and Copy-overlap Aware Evaluation Protocol for Segment-level Video Copy Detection","date":"2022-03-05","arxiv_id":"2203.02654","repositories_listed":1,"syntology":null},{"url":"/paper/just-rank-rethinking-evaluation-with-word-and","slug":"just-rank-rethinking-evaluation-with-word-and","title":"Just Rank: Rethinking Evaluation with Word and Sentence Similarities","date":"2022-03-05","arxiv_id":"2203.02679","repositories_listed":1,"syntology":null},{"url":"/paper/benchmark-evaluation-of-counterfactual","slug":"benchmark-evaluation-of-counterfactual","title":"Benchmarking Instance-Centric Counterfactual Algorithms for XAI: From White Box to Black Box","date":"2022-03-04","arxiv_id":"2203.02399","repositories_listed":1,"syntology":null},{"url":"/paper/hoi4d-a-4d-egocentric-dataset-for-category","slug":"hoi4d-a-4d-egocentric-dataset-for-category","title":"HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction","date":"2022-03-03","arxiv_id":"2203.01577","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/hoi4d-a-4d-egocentric-dataset-for-category#ran","syntology_url":"https://syntology.ai/paper/2203.01577","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.01577"}},"official":{"repos":["leolyliu/HOI4D-Instructions"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/kamnet-an-integrated-spatiotemporal-deep","slug":"kamnet-an-integrated-spatiotemporal-deep","title":"KamNet: An Integrated Spatiotemporal Deep Neural Network for Rare Event Search in KamLAND-Zen","date":"2022-03-03","arxiv_id":"2203.01870","repositories_listed":1,"syntology":null},{"url":"/paper/3d-common-corruptions-and-data-augmentation","slug":"3d-common-corruptions-and-data-augmentation","title":"3D Common Corruptions and Data Augmentation","date":"2022-03-02","arxiv_id":"2203.01441","repositories_listed":1,"syntology":{"n":12,"n_ran":7,"n_constructed":0,"n_ran_checked":1,"n_instrument":6,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":12,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/3d-common-corruptions-and-data-augmentation#ran","syntology_url":"https://syntology.ai/paper/2203.01441","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.01441"}},"official":{"repos":["EPFL-VILAB/3DCommonCorruptions"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/mukayese-turkish-nlp-strikes-back-1","slug":"mukayese-turkish-nlp-strikes-back-1","title":"Mukayese: Turkish NLP Strikes Back","date":"2022-03-02","arxiv_id":"2203.01215","repositories_listed":1,"syntology":null},{"url":"/paper/a-predictive-analytics-approach-for-stroke","slug":"a-predictive-analytics-approach-for-stroke","title":"A predictive analytics approach for stroke prediction using machine learning and neural networks","date":"2022-03-01","arxiv_id":"2203.00497","repositories_listed":1,"syntology":null},{"url":"/paper/towards-iid-representation-learning-and-its","slug":"towards-iid-representation-learning-and-its","title":"Towards IID representation learning and its application on biomedical data","date":"2022-03-01","arxiv_id":"2203.00332","repositories_listed":1,"syntology":null},{"url":"/paper/graphworld-fake-graphs-bring-real-insights","slug":"graphworld-fake-graphs-bring-real-insights","title":"GraphWorld: Fake Graphs Bring Real Insights for GNNs","date":"2022-02-28","arxiv_id":"2203.00112","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/graphworld-fake-graphs-bring-real-insights#ran","syntology_url":"https://syntology.ai/paper/2203.00112","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.00112"}},"official":{"repos":["google-research/graphworld"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/benchmarking-generative-latent-variable","slug":"benchmarking-generative-latent-variable","title":"Benchmarking Generative Latent Variable Models for Speech","date":"2022-02-22","arxiv_id":"2202.12707","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/benchmarking-generative-latent-variable#ran","syntology_url":"https://syntology.ai/paper/2202.12707","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.12707"}},"official":{"repos":["jakobhavtorn/benchmarking-lvms"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/how-to-manage-tiny-machine-learning-at-scale","slug":"how-to-manage-tiny-machine-learning-at-scale","title":"How to Manage Tiny Machine Learning at Scale: An Industrial Perspective","date":"2022-02-18","arxiv_id":"2202.09113","repositories_listed":1,"syntology":null},{"url":"/paper/multires-netvlad-augmenting-place-recognition","slug":"multires-netvlad-augmenting-place-recognition","title":"MultiRes-NetVLAD: Augmenting Place Recognition Training with Low-Resolution Imagery","date":"2022-02-18","arxiv_id":"2202.09146","repositories_listed":1,"syntology":null},{"url":"/paper/benchmarking-missing-values-approaches-for","slug":"benchmarking-missing-values-approaches-for","title":"Benchmarking missing-values approaches for predictive models on health databases","date":"2022-02-17","arxiv_id":"2202.10580","repositories_listed":1,"syntology":null},{"url":"/paper/a-comprehensive-benchmark-of-deep-learning","slug":"a-comprehensive-benchmark-of-deep-learning","title":"Benchmarking of DL Libraries and Models on Mobile Devices","date":"2022-02-14","arxiv_id":"2202.06512","repositories_listed":1,"syntology":null},{"url":"/paper/metashift-a-dataset-of-datasets-for-1","slug":"metashift-a-dataset-of-datasets-for-1","title":"MetaShift: A Dataset of Datasets for Evaluating Contextual Distribution Shifts and Training Conflicts","date":"2022-02-14","arxiv_id":"2202.06523","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/metashift-a-dataset-of-datasets-for-1#ran","syntology_url":"https://syntology.ai/paper/2202.06523","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.06523"}},"official":{"repos":["weixin-liang/metashift"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/wukong-100-million-large-scale-chinese-cross","slug":"wukong-100-million-large-scale-chinese-cross","title":"Wukong: A 100 Million Large-scale Chinese Cross-modal Pre-training Benchmark","date":"2022-02-14","arxiv_id":"2202.06767","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/wukong-100-million-large-scale-chinese-cross#ran","syntology_url":"https://syntology.ai/paper/2202.06767","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.06767"}},"official":null}},{"url":"/paper/comparative-study-between-distance-measures","slug":"comparative-study-between-distance-measures","title":"Comparative Study Between Distance Measures On Supervised Optimum-Path Forest Classification","date":"2022-02-08","arxiv_id":"2202.03854","repositories_listed":1,"syntology":null},{"url":"/paper/ecrecer-enzyme-commission-number","slug":"ecrecer-enzyme-commission-number","title":"ECRECer: Enzyme Commission Number Recommendation and Benchmarking based on Multiagent Dual-core Learning","date":"2022-02-08","arxiv_id":"2202.03632","repositories_listed":1,"syntology":null},{"url":"/paper/what-are-the-best-systems-new-perspectives-on","slug":"what-are-the-best-systems-new-perspectives-on","title":"What are the best systems? New perspectives on NLP Benchmarking","date":"2022-02-08","arxiv_id":"2202.03799","repositories_listed":1,"syntology":null},{"url":"/paper/benchmarking-deep-models-for-salient-object","slug":"benchmarking-deep-models-for-salient-object","title":"Benchmarking Deep Models for Salient Object Detection","date":"2022-02-07","arxiv_id":"2202.02925","repositories_listed":1,"syntology":null},{"url":"/paper/recover-sequential-model-optimization","slug":"recover-sequential-model-optimization","title":"RECOVER: sequential model optimization platform for combination drug repurposing identifies novel synergistic compounds in vitro","date":"2022-02-07","arxiv_id":"2202.04202","repositories_listed":1,"syntology":null},{"url":"/paper/theory-inspired-parameter-control-benchmarks","slug":"theory-inspired-parameter-control-benchmarks","title":"Theory-inspired Parameter Control Benchmarks for Dynamic Algorithm Configuration","date":"2022-02-07","arxiv_id":"2202.03259","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/theory-inspired-parameter-control-benchmarks#ran","syntology_url":"https://syntology.ai/paper/2202.03259","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.03259"}},"official":{"repos":["caroladoerr/leadingonedac"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}}],"record_sha256":"bd0c67f68f3619763c36e5a4d3a5612385ba3a053c51d7aafc1885b17a633828","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}